---
license: mit
---
# 🤖 GAD-GPT-5-Chat-Llama-3.1-8B-Instruct

- The model checkpoint in [Black-Box On-Policy Distillation of Large Language Models](https://arxiv.org/abs/2511.10643) paper. Homepage at [here](https://ytianzhu.github.io/Generative-Adversarial-Distillation/).
- The model is trained with GAD (Generative Adversarial Distillation) from student Llama-3.1-8B-Instruct with teacher GPT-5-Chat.